| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.19533634185791, | |
| "min": 3.1669719219207764, | |
| "max": 3.2957513332366943, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 68917.015625, | |
| "min": 28434.181640625, | |
| "max": 105464.015625, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 999.0, | |
| "min": 526.6666666666666, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19980.0, | |
| "min": 15628.0, | |
| "max": 26936.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1198.0420076087978, | |
| "min": 1194.2184049994214, | |
| "max": 1201.7095063467, | |
| "count": 64 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 2396.0840152175956, | |
| "min": 2390.0967404942567, | |
| "max": 11988.941960091657, | |
| "count": 64 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 999844.0, | |
| "min": 9484.0, | |
| "max": 999844.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 999844.0, | |
| "min": 9484.0, | |
| "max": 999844.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.009531398303806782, | |
| "min": -0.028105400502681732, | |
| "max": 0.01449987106025219, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.09531398117542267, | |
| "min": -0.3372648060321808, | |
| "max": 0.18849831819534302, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.008838149718940258, | |
| "min": -0.029740313068032265, | |
| "max": 0.01381057221442461, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.08838149905204773, | |
| "min": -0.3568837642669678, | |
| "max": 0.1690513789653778, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.0, | |
| "min": -0.5714285714285714, | |
| "max": 0.19809230932822594, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 0.0, | |
| "min": -8.0, | |
| "max": 2.5752000212669373, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": -0.5714285714285714, | |
| "max": 0.19809230932822594, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": -8.0, | |
| "max": 2.5752000212669373, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01588540293741971, | |
| "min": 0.011148569887154736, | |
| "max": 0.021742360728482405, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01588540293741971, | |
| "min": 0.011148569887154736, | |
| "max": 0.021742360728482405, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0009573467609394963, | |
| "min": 9.311301473265606e-07, | |
| "max": 0.005382450468217333, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0009573467609394963, | |
| "min": 9.311301473265606e-07, | |
| "max": 0.005382450468217333, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.0009645330506221701, | |
| "min": 1.2156386522595615e-06, | |
| "max": 0.0055860036906475825, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.0009645330506221701, | |
| "min": 1.2156386522595615e-06, | |
| "max": 0.0055860036906475825, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 46 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 46 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1678727149", | |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.11.0+cu102", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1678729238" | |
| }, | |
| "total": 2088.815020232, | |
| "count": 1, | |
| "self": 0.4385623659995872, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.16163720000008652, | |
| "count": 1, | |
| "self": 0.16163720000008652 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2088.2148206660004, | |
| "count": 1, | |
| "self": 1.4529292570341568, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 7.2116242549993785, | |
| "count": 6, | |
| "self": 7.2116242549993785 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2079.2593675359662, | |
| "count": 65224, | |
| "self": 1.6912534419216172, | |
| "children": { | |
| "env_step": { | |
| "total": 1659.8995953189947, | |
| "count": 65224, | |
| "self": 1300.745286861065, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 358.27748184693655, | |
| "count": 65224, | |
| "self": 10.75518702793238, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 347.5222948190042, | |
| "count": 129560, | |
| "self": 347.5222948190042 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.876826610993021, | |
| "count": 65224, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2083.6253783800025, | |
| "count": 65224, | |
| "is_parallel": true, | |
| "self": 986.7496462200538, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.004120793000083722, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0010642839999945863, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.003056509000089136, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.003056509000089136 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.037904391999973086, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.001060361000327248, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0007708050000019284, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007708050000019284 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.03285783699993772, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.03285783699993772 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0032153889997061924, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006746859999111621, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0025407029997950303, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0025407029997950303 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1096.8658263499492, | |
| "count": 65223, | |
| "is_parallel": true, | |
| "self": 62.820905666929775, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 44.15425392503403, | |
| "count": 65223, | |
| "is_parallel": true, | |
| "self": 44.15425392503403 | |
| }, | |
| "communicator.exchange": { | |
| "total": 793.7561593879473, | |
| "count": 65223, | |
| "is_parallel": true, | |
| "self": 793.7561593879473 | |
| }, | |
| "steps_from_proto": { | |
| "total": 196.13450737003814, | |
| "count": 130446, | |
| "is_parallel": true, | |
| "self": 36.081435931882424, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 160.0530714381557, | |
| "count": 521784, | |
| "is_parallel": true, | |
| "self": 160.0530714381557 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.009905809999509074, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0018407020006634411, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.008065107998845633, | |
| "count": 32, | |
| "is_parallel": true, | |
| "self": 0.008065107998845633 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 417.66851877504996, | |
| "count": 65224, | |
| "self": 13.551541000070984, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 107.03329781098091, | |
| "count": 65224, | |
| "self": 106.4232389519807, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.610058859000219, | |
| "count": 2, | |
| "self": 0.610058859000219 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 297.08367996399807, | |
| "count": 46, | |
| "self": 187.63886887799367, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 109.44481108600439, | |
| "count": 1380, | |
| "self": 109.44481108600439 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0160001693293452e-06, | |
| "count": 1, | |
| "self": 1.0160001693293452e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.29089860200019757, | |
| "count": 1, | |
| "self": 0.001919720000387315, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.28897888199981026, | |
| "count": 1, | |
| "self": 0.28897888199981026 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |